From e7fe6cae144b97f1f33a1def2a1150ca219cf6ba Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Mon, 27 Apr 2026 21:41:48 +0000
Subject: [PATCH] fix(normalize): discard user/gemini turns before
 session_metadata sentinel

Agent-Logs-Url: https://github.com/MemPalace/mempalace/sessions/4511e9aa-38e7-440e-a6f8-eda91e576f0f

Co-authored-by: igorls <4753812+igorls@users.noreply.github.com>
---
 mempalace/normalize.py  | 14 +++++++++++---
 tests/test_normalize.py | 19 +++++++++++++++++++
 2 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/mempalace/normalize.py b/mempalace/normalize.py
index 9326a62..4252afa 100644
--- a/mempalace/normalize.py
+++ b/mempalace/normalize.py
@@ -296,9 +296,12 @@ def _try_gemini_jsonl(content: str) -> Optional[str]:
 
     Detection requires a ``session_metadata`` record so this parser does
     not false-positive against Claude Code or Codex JSONL passed through
-    the dispatch chain. ``message_update`` entries are skipped — they
-    have no message text. Multiple text blocks within a single message's
-    content array are concatenated in order, separated by newlines.
+    the dispatch chain. Any ``user``/``gemini`` lines that appear before
+    ``session_metadata`` are discarded — they are treated as preamble
+    noise, not conversational turns. ``message_update`` entries are
+    skipped — they have no message text. Multiple text blocks within a
+    single message's content array are concatenated in order, separated
+    by newlines.
     """
     lines = [line.strip() for line in content.strip().split("\n") if line.strip()]
     messages = []
@@ -316,6 +319,11 @@ def _try_gemini_jsonl(content: str) -> Optional[str]:
             has_session_metadata = True
             continue
 
+        # Discard everything (including user/gemini turns) until the
+        # session_metadata sentinel has been seen.
+        if not has_session_metadata:
+            continue
+
         if entry_type not in ("user", "gemini"):
             # Skips message_update, system events, anything else.
             continue
diff --git a/tests/test_normalize.py b/tests/test_normalize.py
index be408d5..2b0f180 100644
--- a/tests/test_normalize.py
+++ b/tests/test_normalize.py
@@ -594,6 +594,25 @@ def test_gemini_jsonl_does_not_match_codex():
     assert result is None
 
 
+def test_gemini_jsonl_messages_before_session_metadata_discarded():
+    """user/gemini turns that appear before the session_metadata sentinel must
+    be silently discarded, not counted as conversational messages.  Only turns
+    after the sentinel contribute to the transcript."""
+    lines = [
+        json.dumps({"type": "user", "content": [{"text": "preamble Q"}]}),
+        json.dumps({"type": "gemini", "content": [{"text": "preamble A"}]}),
+        json.dumps({"type": "session_metadata", "sessionId": "s"}),
+        json.dumps({"type": "user", "content": [{"text": "real Q"}]}),
+        json.dumps({"type": "gemini", "content": [{"text": "real A"}]}),
+    ]
+    result = _try_gemini_jsonl("\n".join(lines))
+    assert result is not None
+    assert "preamble Q" not in result
+    assert "preamble A" not in result
+    assert "> real Q" in result
+    assert "real A" in result
+
+
 # ── _try_claude_ai_json ───────────────────────────────────────────────